Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1911 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.7907. Min Act: -0.0001

Data Index: 311326 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.7362. Min Act: -0.0000

Data Index: 424982 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.8042. Min Act: -0.0001

Data Index: 325042 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.8022. Min Act: -0.0000

Data Index: 506957 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.7390. Min Act: -0.0001

Data Index: 223439 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.7350. Min Act: -0.0001

Data Index: 691608 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.6847. Min Act: -0.0000

Data Index: 208558 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.5875. Min Act: -0.0001

Data Index: 792228 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.7339. Min Act: -0.0000

Data Index: 1259026 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.6806. Min Act: -0.0000

Data Index: 1201803 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.6603. Min Act: -0.0001

Data Index: 1272842 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.7017. Min Act: -0.0000

Data Index: 459083 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.6653. Min Act: -0.0001

Data Index: 681755 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.5652. Min Act: -0.0000

Data Index: 1035643 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.6339. Min Act: -0.0001

Data Index: 8952 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.6478. Min Act: -0.0001

Data Index: 934013 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.6272. Min Act: -0.0001

Data Index: 666530 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.5871. Min Act: -0.0001

Data Index: 406798 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.6377. Min Act: -0.0000

Data Index: 77694 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.6275. Min Act: -0.0001

Data Index: 115283 (C4 (Web Text))

Max Activating Token Index: 130